# Neural Compositional Rule Learning for Knowledge Graph Reasoning

arXiv: https://arxiv.org/abs/2303.03581 · HTML: https://mlsanity.com/paper/2303.03581/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 7 Mar 2023.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Compositionality decomposed: how do neural networks generalise?](https://mlsanity.com/paper/1908.08351/) (2019)
- [DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs](https://mlsanity.com/paper/1911.00055/) (2019)
- [CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text](https://mlsanity.com/paper/1908.06177/) (2019)
- [End-to-End Differentiable Proving](https://mlsanity.com/paper/1705.11040/) (2017)
- [RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2010.04029/) (2020)
- [Learning Reasoning Strategies in End-to-End Differentiable Proving](https://mlsanity.com/paper/2007.06477/) (2020)
- [Learn to Explain Efficiently via Neural Logic Inductive Learning](https://mlsanity.com/paper/1910.02481/) (2019)
- [Differentiable Reasoning on Large Knowledge Bases and Natural Language](https://mlsanity.com/paper/1912.10824/) (2019)
- [Neuro-Symbolic Hierarchical Rule Induction](https://mlsanity.com/paper/2112.13418/) (2021)
- [Logical Rule Induction and Theory Learning Using Neural Theorem Proving](https://mlsanity.com/paper/1809.02193/) (2018)
- [Evaluating Logical Generalization in Graph Neural Networks](https://mlsanity.com/paper/2003.06560/) (2020)
- [R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning](https://mlsanity.com/paper/2205.06454/) (2022)

## Built on by (most cited first, 20 of 20)

- [ChatRule: Mining Logical Rules with Large Language Models for Knowledge Graph Reasoning](https://mlsanity.com/paper/2309.01538/) (2023)
- [Evaluating Deep Unlearning in Large Language Models](https://mlsanity.com/paper/2410.15153/) (2024)
- [Structure Guided Multi-modal Pre-trained Transformer for Knowledge Graph Reasoning](https://mlsanity.com/paper/2307.03591/) (2023)
- [Neuro-Symbolic Entity Alignment via Variational Inference](https://mlsanity.com/paper/2410.04153/) (2024)
- [Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion](https://mlsanity.com/paper/2407.16127/) (2024)
- [Gold: A Global and Local-aware Denoising Framework for Commonsense Knowledge Graph Noise Detection](https://mlsanity.com/paper/2310.12011/) (2023)
- [Systematic Relational Reasoning With Epistemic Graph Neural Networks](https://mlsanity.com/paper/2407.17396/) (2024)
- [RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.08862/) (2025)
- [Efficient Learning on Large Graphs using a Densifying Regularity Lemma](https://mlsanity.com/paper/2504.18273/) (2025)
- [When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning](https://mlsanity.com/paper/2510.23532/) (2025)
- [Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era](https://mlsanity.com/paper/2603.03177/) (2026)
- [Efficiently Learning Probabilistic Logical Models by Cheaply Ranking Mined Rules](https://mlsanity.com/paper/2409.16238/) (2024)
- [Resilience in Knowledge Graph Embeddings](https://mlsanity.com/paper/2410.21163/) (2024)
- [CHAINSFORMER: Numerical Reasoning on Knowledge Graphs from a Chain Perspective](https://mlsanity.com/paper/2504.14282/) (2025)
- [GLIDR: Graph-Like Inductive Logic Programming with Differentiable Reasoning](https://mlsanity.com/paper/2508.06716/) (2025)
- [Neural Probabilistic Logic Learning for Knowledge Graph Reasoning](https://mlsanity.com/paper/2407.03704/) (2024)
- [Rule Learning for Knowledge Graph Reasoning under Agnostic Distribution Shift](https://mlsanity.com/paper/2507.05110/) (2025)
- [SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completion](https://mlsanity.com/paper/2510.00279/) (2025)
- [Project Auto-World: Towards Automated Benchmarking of Neural Relational Reasoners](https://mlsanity.com/paper/2606.24965/) (2026)
- [Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge](https://mlsanity.com/paper/2609.36620/) (2026)

## Abstract (arXiv)

Learning logical rules is critical to improving reasoning in KGs. This is due to their ability to provide logical and interpretable explanations when used for predictions, as well as their ability to generalize to other tasks, domains, and data. While recent methods have been proposed to learn logical rules, the majority of these methods are either restricted by their computational complexity and can not handle the large search space of large-scale KGs, or show poor generalization when exposed to data outside the training set. In this paper, we propose an end-to-end neural model for learning compositional logical rules called NCRL. NCRL detects the best compositional structure of a rule body, and breaks it into small compositions in order to infer the rule head. By recurrently merging compositions in the rule body with a recurrent attention unit, NCRL finally predicts a single rule head. Experimental results show that NCRL learns high-quality rules, as well as being generalizable. Specifically, we show that NCRL is scalable, efficient, and yields state-of-the-art results for knowledge graph completion on large-scale KGs. Moreover, we test NCRL for systematic generalization by learning to reason on small-scale observed graphs and evaluating on larger unseen ones.